Python中 Pandas 50題衝關

參考資料 | 100-pandas-puzzles - GitHub | Pandas 百題大衝關

基本操作導入 Pandas 庫並簡寫為 pd，並輸出版本號

import pandas as pd
pd.__version__

arr = [0, 1, 2, 3, 4]
df = pd.Series(arr) # 如果不指定索引，則默認從 0 開始
df

d = {'a':1,'b':2,'c':3,'d':4,'e':5}
df = pd.Series(d)
df

dates = pd.date_range('today',periods=6) # 定義時間序列作為 index
num_arr = np.random.randn(6,4) # 傳入 numpy 隨機數組
columns = ['A','B','C','D'] # 將列表作為列名
df = pd.DataFrame(num_arr, index = dates, columns = columns)
df

從CSV中創建 DataFrame，分隔符為「；」，編碼格式為gbk

df = pd.read_csv('test.csv', encoding='gbk, sep=';')

import numpy as np

data = {'animal': ['cat', 'cat', 'snake', 'dog', 'dog', 'cat', 'snake', 'cat', 'dog', 'dog'],
'age': [2.5, 3, 0.5, np.nan, 5, 2, 4.5, np.nan, 7, 3],
'visits': [1, 3, 2, 3, 2, 3, 1, 1, 2, 1],
'priority': ['yes', 'yes', 'no', 'yes', 'no', 'no', 'no', 'yes', 'no', 'no']}

labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j']

df = pd.DataFrame(data, index=labels)
df

顯示df的基礎信息，包括行的數量；列名；每一列值的數量、類型

df.info()
# 方法二
# df.describe()

df.iloc[:3]
# 方法二
#df.head(3)

df.loc[:, ['animal', 'age']]
# 方法二
# df[['animal', 'age']]

取出索引為[3, 4, 8]行的animal和age列

df.loc[df.index[[3, 4, 8]], ['animal', 'age']]

df[df['age'] > 3]

df[df['age'].isnull()]

df[(df['age']>2) & (df['age']>4)]
# 方法二
# df[df['age'].between(2, 4)]

df.loc['f', 'age'] = 1.5

df['visits'].sum()

df.groupby('animal')['age'].mean()

#插入
df.loc['k'] = [5.5, 'dog', 'no', 2]
# 刪除
df = df.drop('k')
df

df['animal'].value_counts()

df.sort_values(by=['age', 'visits'], ascending=[False, True])

將priority列中的yes, no替換為布爾值True, False

df['priority'] = df['priority'].map({'yes': True, 'no': False})
df

df['animal'] = df['animal'].replace('snake', 'python')
df

對每種animal的每種不同數量visits，計算平均age，即，返回一個表格，行是aniaml種類，列是visits數量，表格值是行動物種類列訪客數量的平均年齡

df.pivot_table(index='animal', columns='visits', values='age', aggfunc='mean')

 

進階操作有一列整數列A的DatraFrame，刪除數值重複的行

df = pd.DataFrame({'A': [1, 2, 2, 3, 4, 5, 5, 5, 6, 7, 7]})
print(df)
df1 = df.loc[df['A'].shift() != df['A']]
# 方法二
# df1 = df.drop_duplicates(subset='A')
print(df1)

一個全數值DatraFrame，每個數字減去該行的平均數

df = pd.DataFrame(np.random.random(size=(5, 3)))
print(df)
df1 = df.sub(df.mean(axis=1), axis=0)
print(df1)

df = pd.DataFrame(np.random.random(size=(5, 5)), columns=list('abcde'))
print(df)
df.sum().idxmin()

給定DataFrame，求A列每個值的前3的B的值的和

df = pd.DataFrame({'A': list('aaabbcaabcccbbc'),
'B': [12,345,3,1,45,14,4,52,54,23,235,21,57,3,87]})
print(df)
df1 = df.groupby('A')['B'].nlargest(3).sum(level=0)
print(df1)

給定DataFrame，有列A, B，A的值在1-100（含），對A列每10步長，求對應的B的和

df = pd.DataFrame({'A': [1,2,11,11,33,34,35,40,79,99],
'B': [1,2,11,11,33,34,35,40,79,99]})
print(df)
df1 = df.groupby(pd.cut(df['A'], np.arange(0, 101, 10)))['B'].sum()
print(df1)

給定DataFrame，計算每個元素至左邊最近的0（或者至開頭）的距離，生成新列y

df = pd.DataFrame({'X': [7, 2, 0, 3, 4, 2, 5, 0, 3, 4]})

izero = np.r_[-1, (df['X'] == 0).to_numpy().nonzero()[0]] # 標記0的位置
idx = np.arange(len(df))
df['Y'] = idx - izero[np.searchsorted(izero - 1, idx) - 1]
print(df)

# 方法二
# x = (df['X'] != 0).cumsum()
# y = x != x.shift()
# df['Y'] = y.groupby((y != y.shift()).cumsum()).cumsum()

# 方法三
# df['Y'] = df.groupby((df['X'] == 0).cumsum()).cumcount()
#first_zero_idx = (df['X'] == 0).idxmax()
# df['Y'].iloc[0:first_zero_idx] += 1

一個全數值的DataFrame，返回最大3個值的坐標

df = pd.DataFrame(np.random.random(size=(5, 3)))
print(df)
df.unstack().sort_values()[-3:].index.tolist()

df = pd.DataFrame({'grps': list('aaabbcaabcccbbc'),
'vals': [-12,345,3,1,45,14,4,-52,54,23,-235,21,57,3,87]})
print(df)

def replace(group):
mask = group<0
group[mask] = group[~mask].mean()
return group

df['vals'] = df.groupby(['grps'])['vals'].transform(replace)
print(df)

df = pd.DataFrame({'group': list('aabbabbbabab'),
'value': [1, 2, 3, np.nan, 2, 3, np.nan, 1, 7, 3, np.nan, 8]})
print(df)

g1 = df.groupby(['group'])['value']
g2 = df.fillna(0).groupby(['group'])['value']

s = g2.rolling(3, min_periods=1).sum() / g1.rolling(3, min_periods=1).count()
s.reset_index(level=0, drop=True).sort_index()

 

Series 和 Datetime索引創建Series s，將2015所有工作日作為隨機值的索引

dti = pd.date_range(start='2015-01-01', end='2015-12-31', freq='B')
s = pd.Series(np.random.rand(len(dti)), index=dti)

s.head(10)

s[s.index.weekday == 2].sum()

s.resample('M').mean()

s.groupby(pd.Grouper(freq='4M')).idxmax()

pd.date_range('2015-01-01', '2016-12-31', freq='WOM-3THU')

 

數據清洗

df = pd.DataFrame({'From_To': ['LoNDon_paris', 'MAdrid_miLAN', 'londON_StockhOlm',
'Budapest_PaRis', 'Brussels_londOn'],
'FlightNumber': [10045, np.nan, 10065, np.nan, 10085],
'RecentDelays': [[23, 47], [], [24, 43, 87], [13], [67, 32]],
'Airline': ['KLM(!)', '<Air France> (12)', '(British Airways. )',
'12. Air France', '"Swiss Air"']})
df

FlightNumber列中有些值缺失了，他們本來應該是每一行增加10，填充缺失的數值，並且令數據類型為整數

df['FlightNumber'] = df['FlightNumber'].interpolate().astype(int)
df

將From_To列從_分開，分成From, To兩列，並刪除原始列

temp = df.From_To.str.split('_', expand=True)
temp.columns = ['From', 'To']
df = df.join(temp)
df = df.drop('From_To', axis=1)
df

df['From'] = df['From'].str.capitalize()
df['To'] = df['To'].str.capitalize()
df

Airline列，有一些多餘的標點符號，需要提取出正確的航司名稱。舉例：'(British Airways. )' 應該改為 'British Airways'.

df['Airline'] = df['Airline'].str.extract('([a-zA-Z\s]+)', expand=False).str.strip()
df

Airline列，數據被以列表的形式錄入，但是我們希望每個數字被錄入成單獨一列，delay_1, delay_2, ...沒有的用NAN替代。

delays = df['RecentDelays'].apply(pd.Series)
delays.columns = ['delay_{}'.format(n) for n in range(1, len(delays.columns)+1)]
df = df.drop('RecentDelays', axis=1).join(delays)
df

 

層次化索引用 letters = ['A', 'B', 'C']和 numbers = list(range(10))的組合作為系列隨機值的層次化索引

letters = ['A', 'B', 'C']
numbers = list(range(4))

mi = pd.MultiIndex.from_product([letters, numbers])
s = pd.Series(np.random.rand(12), index=mi)
s

s.index.is_lexsorted()
# 方法二
# s.index.lexsort_depth == s.index.nlevels

s.loc[:, [1, 3]]

對s進行切片操作，取一級索引至B，二級索引從2開始到最後

s.loc[pd.IndexSlice[:'B', 2:]]
# 方法二
# s.loc[slice(None, 'B'), slice(2, None)]

46.計算每個一級索引的和（A, B, C每一個的和）

s.sum(level=0)
#方法二
#s.unstack().sum(axis=0)

交換索引等級，新的Series是字典順序嗎？不是的話請排序

new_s = s.swaplevel(0, 1)
print(new_s)
print(new_s.index.is_lexsorted())
new_s = new_s.sort_index()
print(new_s)

 

可視化

import matplotlib.pyplot as plt
df = pd.DataFrame({"xs":[1,5,2,8,1], "ys":[4,2,1,9,6]})
plt.style.use('ggplot')

df.plot.scatter("xs", "ys", color = "black", marker = "x")

df = pd.DataFrame({"productivity":[5,2,3,1,4,5,6,7,8,3,4,8,9],
"hours_in" :[1,9,6,5,3,9,2,9,1,7,4,2,2],
"happiness" :[2,1,3,2,3,1,2,3,1,2,2,1,3],
"caffienated" :[0,0,1,1,0,0,0,0,1,1,0,1,0]})

df.plot.scatter("hours_in", "productivity", s = df.happiness * 100, c = df.caffienated)

df = pd.DataFrame({"revenue":[57,68,63,71,72,90,80,62,59,51,47,52],
"advertising":[2.1,1.9,2.7,3.0,3.6,3.2,2.7,2.4,1.8,1.6,1.3,1.9],
"month":range(12)})

ax = df.plot.bar("month", "revenue", color = "green")
df.plot.line("month", "advertising", secondary_y = True, ax = ax)
ax.set_xlim((-1,12));